Pith. sign in

Generating natural language adversarial examples

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CR 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

background 1

representative citing papers

Adversarial Text Generation with Dynamic Contextual Perturbation

cs.CR · 2025-06-10 · reject · novelty 4.0

An NLP attack that swaps gradient-important words with synonyms while minimizing BERT embedding distance is reported to beat PWWS and BERT-Attack on accuracy drop, perturbation rate, and queries, but the paper gives no code or full setup.

citing papers explorer

Showing 1 of 1 citing paper.

  • Adversarial Text Generation with Dynamic Contextual Perturbation cs.CR · 2025-06-10 · reject · none · ref 3

    An NLP attack that swaps gradient-important words with synonyms while minimizing BERT embedding distance is reported to beat PWWS and BERT-Attack on accuracy drop, perturbation rate, and queries, but the paper gives no code or full setup.